how to get your cvpr paper rejected? ming-hsuan yang

How to Get Your CVPR Paper Rejected?

Ming-Hsuan Yang

Outline

• Conferences• Journals• Writing• Presentation• Lessons

Conferences

• CVPR – Computer Vision and Pattern Recognition, since 1983– Annual, held in US

• ICCV – International Conference on Computer Vision, since 1987– Every other year, alternate in 3

continents• ECCV – European Conference on

Computer Vision, since 1990– Every other year, held in Europe

Conferences

• ACCV – Asian Conference on Computer Vision

• BMVC – British Machine Vision Conference

• ICPR – International Conference on Pattern Recognition

• SIGGRAPH• NIPS – Neural Information Processing

Systems

Conferences

• MICCAI – Medical Image Computing and Computer-Assisted Intervention

• FG – IEEE Conference on Automatic Face and Gesture Recognition

• ICCP – IEEE International Conference on Computational Photography

• ICML – International Conference on Machine Learning

• IJCAI, AAAI, MVA, ICDR, ICVS, DAGM, CAIP, ICRA, ICASSP, ICIP, SPIE, DCC, WACV, 3DPVT, ACM Multimedia, ICME, …

Conference Location

Conference Location

• Me and confernece I want to attend (location vs reputation)

Conference Organization

• General chairs: administration• Program chairs: handling papers• Area chairs:

– Assign reviewers– Read reviews and rebuttals– Consolidation reports– Recommendation

• Reviewers• Authors

Review Process

• Submission• CVPR/ECCV/ICCV

– Double blind review– Program chairs: assign papers to area

chairs– Area chairs: assign papers to reviewers

• Rebuttal• Results

Area Chair Meetings

• 2 day meetings• Several panels• Each paper is reviewed by at least 2

area chairs• Buddy system• Area chair make recommendations• Program chairs make final decisions

Triage

• Area chairs know the reviewers• Reviews are weighted • Based on reviews and rebuttal

– Accept: (decide oral later)– Reject: don’t waste time – Go either way: lots of papers

• Usually agree with reviewers but anything can happen as long as there are good justifications

Conference Acceptance Rate• ICCV/CVPR/ECCV: ~ 25%• ACCV (2009): ~ 30%• NIPS: ~ 25%• BMVC: ~ 30%• ICIP: ~ 45%• ICPR: ~ 55%

• Disclaimer– low acceptance rate = high quality?

CVPR

Overall

Oral Submission

96 97 98 99 00 01 03 04 05 06 07 08 09 10 11 12 130

200

400

600

800

1000

1200

1400

1600

1800

2000

551 544453 504 466

920 9051000

116011311250

1593

1450

17241677

1933

1798

96 97 98 99 00 01 03 04 05 06 07 08 09 10 11 12 130.00%

2.00%

4.00%

6.00%

8.00%

10.00%

12.00%

14.00%

16.00%

11.62%11.40%

9.27%

11.90%

14.16%

8.15%

6.63%

5.40%

6.38%

4.77% 4.80%

3.95%4.21%

4.52%

3.52%

2.48%

3.34%

96 97 98 99 00 01 03 04 05 06 07 08 09 10 11 12 130.00%

5.00%

10.00%

15.00%

20.00%

25.00%

30.00%

35.00%

40.00%

45.00%

50.00%

24.86%

31.80%30.68%29.76%

47.21%

29.67%

23.09%

26.00%28.02%28.12%28.24%

31.89%

26.41%26.74%26.12%24.06%

26.25%

ICCV

Overall

Oral Submission

98 99 01 03 05 07 09 110

200

400

600

800

1000

1200

1400

550 575 596

966

1230 1190

13271216

98 99 01 03 05 07 09 110.00%

1.00%

2.00%

3.00%

4.00%

5.00%

6.00%

7.00%

8.00%

9.00%

7.45%8.00%

7.55%

4.45%

3.66% 3.95%3.62% 3.70%

98 99 01 03 05 07 09 110.00%

5.00%

10.00%

15.00%

20.00%

25.00%

30.00%

35.00%

40.00%

30.36%28.35%

34.40%

20.60% 19.84%

23.53% 23.21%

27.96%

ECCV

Overall

Oral Submission

98 00 02 04 06 08 10 120

200

400

600

800

1000

1200

1400

1600

223 266

600 555

900 871

1174

1437

98 00 02 04 06 08 10 120.00%

2.00%

4.00%

6.00%

8.00%

10.00%

12.00%

14.00%

16.00%

18.00%

20.00% 18.83%

16.17%

7.50% 7.39%

4.44% 4.59%3.24% 2.78%

98 00 02 04 06 08 10 120.00%

10.00%

20.00%

30.00%

40.00%

50.00%

60.00%

50.22%

43.61%

37.67%34.23%

21.44%

27.90% 27.43% 28.39%

Top 100 Publications - English• For what it is worth (h5 index by

Google Scholar)1. Nature2. The New England Journal of

Medicine3. Science…63. IEEE Conference on Computer Vision and Pattern Recognition (CVPR)…

Top Publications - E&CS

1. Nano Letters…7. IEEE Conference on Computer Vision and Pattern Recognition (CVPR)...13. IEEE Transactions on Pattern Analysis and Machine Intelligence…

Reactions• Top journal papers• Workshops vs conferences• Waiting for the review and results• Acceptance• Reject• Mixed feeling• Finding an error• Resubmit? • This time, it will go through• Paper finally accepted• Registration• Oral presentation• Poster presentation

Database Community

• Jeffrey Naughton’s ICDE 2010 keynote

• What’s wrong with the reviewing process?

• How to fix that?

Journals

• PAMI – IEEE Transactions on Pattern Analysis and Machine Intelligence, since 1979 (impact factor: 5.96, #1 in all engineering and AI, top-ranked IEEE and CS journal)

• IJCV – International Journal on Computer Vision, since 1988 (impact factor: 5.36, #2 in all engineering and AI)

• CVIU – Computer Vision and Image Understanding, since 1972 (impact factor: 2.20)

Journals

• IVC – Image and Vision Computing• TIP – IEEE Transactions on Image

Processing• TMI- IEEE Transactions on Medical

Imaging • MVA – Machine Vision and

Applications• PR – Pattern Recognition• TMM – IEEE Transactions on

Multimedia• …

PAMI Reviewing Process

• Editor-in-chief (EIC) assigns papers to associate editors (AE)

• AE assigns reviewers• First-round review: 3-6 months

– Accept as is– Accept with minor revision– Major revision– Resubmit as new– Reject

PAMI Reviewing Process

• Second-round review: 2-4 months– Accept as is– Accept with minor revision– Reject

• EIC makes final decision• Overall turn-around time: 6 to 12

months• Rule of thumb: 15% additional work

beyond a CVPR/ICCV/ECCV paper

IJCV/CVIU Reviewing Process

• Similar formats• CVIU has roughly the same turn-

around time as PAMI• IJCV tends to have longer turn-around

time

Journal Acceptance Rate

• PAMI, IJCV: ~ 20% (my guess, no stats)

• CVIU: ~ 30%

From Conferences to Journals• How much additional work?

– 30% additional more work for PAMI?– As long as the journal version is

significantly different from the conference one

• Novelty of each work– Some reviewers still argue against this– Editors usually accept paper with the

same ideas

How to Get Your Paper Rejected?• Jim Kajia (SIGGRAPH 93 papers

chair): How to get your SIGGRAPH paper rejected?

• Do not– Pay attention to review process– Put yourself from a reviewer’s perspective – Put the work in right context– Carry out sufficient amount of experiments– Compare with state-of-the-art algorithms– Pay attention to writing

Review Form

• Summary• Overall Rating

– Definite accept, weakly accept, borderline, weakly reject, definite reject

• Novelty– Very original, original, minor originality, has been done

before

• Importance/relevance– Of broad interest, interesting to a subarea, interesting

only to a small number of attendees, out of CVPR scope

Review Form

• Clarity of presentation– Reads very well, is clear enough, difficult to read,

unreadable

• Technical correctness– Definite correct, probably correct but did not check

completely, contains rectifiable errors, has major problems

• Experimental validation– Excellent validation or N/A (a theoretical paper), limited

but convincing, lacking in some aspects, insufficient validation

• Additional comments• Reviewer’s name

Learn from Reviewing Process• Learn how others/you can pick apart

a paper• Learn from other’s mistakes• Get to see other reviewers evaluate

the same paper• See how authors rebut comments• Learn how to write good papers• Learn what it takes to get a paper

published

Put Yourself as Reviewer

• Reviewer’s perspective• How a paper gets rejected?• What are the contributions?• Does it advance the science in the

filed?• Why you should accept this paper?• Is this paper a case study?• Is this paper interesting?• Who is the audience?

Experimental Validation

• Common data set• Baseline experiment• Killer data set• Large scale experiment• Evaluation metric• Side effects• Comparisons

Compare With State of the Art• Do your homework• Need to know what is out there • Need to show why one’s method

outperforms others, and in what way?– speed? – accuracy? – sensitive to parameters?– assumption– easy to implement? – general application?

Writing

Writing

Writing

• Reviewing a poorly written paper• Clear presentation• Terse• Careful about wording• Make claims with strong evidence

Writing

• Matt Welsh’s blog on scientific writing

• Sharpen your mental focus• Force you to obsess over every

meticulous detail – word choice, word count, overall tone, readability of graphs (and others such as font size, layout and spacing, and page limit)

Writing

• Crystalizing the ideas through the process of putting things together

• Hone the paper to a razor-sharp, articulate, polished work

Writing

• Write the paper as early as possible, sometimes before even starting the research work

• Will discover the important things that you have not thought about

• The process of writing results in a flood of ideas

Writing

• Even if a paper is not accepted, the process is energizing and often lead to new ideas for the next research problems

• Submitting the paper is often the start of a new line of work

• Riding on that clarity of thought would emerge post-deadline (and a much-needed break)

Tell A Good Story

• Good ideas and convincing results• But not too much (vs grant proposal)

Presentation

• Good artists copy, great artists steal• Not just sugar coating• Not just a good spin• Tell a convincing story with solid

evidence• Present your ideas with style• Q&A• Real stories

Interesting Title

• Cool titles attract people• Grab people’s attention• Buzz word?• But don’t be provocative

Math Equations

• Minimal number of equations– No more, no less– Too many details simply make a paper

inaccessible• Too few equations• Many good papers have no or few

equations– CVPR 13 best paper– CVPR 05 HOG paper

Figures

• Be clear• Sufficient number of figures

Theoretical or Applied?

• Computer vision is more applied, at least nowadays

• Theory vs real world• More high impact papers are about

how to get things done right

Common Mistakes

• typos• “a”, “the”• inanimate objects with verbs• inconsistent usage of words

Get Results First than Writing?• Conventional mode

– Idea-> Do research -> Write paper• “How to write a great research paper” by Simon

Peyton Jones– Idea -> Write paper -> Do research

• Forces us to be clear, focused• Crystallizes what we don’t understand• Opens the way to dialogue with others: reality check,

critique, and collaboration

• My take– Idea -> Write paper -> Do research -> Revise paper ->

Do research -> Revise paper -> …

Supplementary Material

• Important• Add more results and large figures• Add technical details as necessary (

don’t miss important details)• Derivation details, e.g.,

proof of a theorem

Most Important Factors

• Novelty• Significant contributions (vs.

salami publishing)• Make sure your paper is non-

rejectable (above the bar with some error margin)

Rebuttal or Response

• Anything can happen:– Good surprise:

• One CVPR paper: BR, BR, DR• Two ECCV papers: PR, PR, BR

– Bad surprise: • Two ECCV papers: PA, PA, BR

Challenging Issues

• Large scale– CVPR 2011 best paper: pose estimation– CVPR 2013 best paper: object detection

• Unconstrained• Real-time

– CVPR 2001: face detector– CVPR 2006: scalable object recognition

• Robustness• Recover from failure

Interesting Stats

• Best papers and top cited papers in computer science

• Best papers = high impact?• Oral papers are more influential?• CVPR Longuet-Hggins prize• ICCV test-of-time award

Data Set Selection

• NIPS 02 by Doudou LaLoudouana and Mambobo Bonouliqui Tarare, Lupano Tecallonou Center, Selacie, Guana

• The secret to publish a paper in machine learning conferences?

• Read the references therein carefully!

Ask Someone to Proofread

• Certainly your advisor• Polish your work

Paper Gestalt

Paper Gestalt

• CVPR 10 by Carven von Bearnensquash, Department of Computer Science, University of Phoenix

• Main Point: Get your paper looking pretty with right mix of equations, tables and figures

Tools

• Google scholar, citeseer• h-index• Software: publish or perish

• Disclaimer:– h index = significance? – # of citation = significance?

Basic Rules

• Use LaTeX• Read authors’ guideline• Read reviewers’ guideline • Print out your paper – what you see may

NOT be what you get• Submit paper right before deadline

– Risky– Exhausting– Murphy’s law

• Do not count on extension

Lessons

• Several influential papers have been rejected once or twice

• Some best papers make little impact• Never give up in the process

Karma?

Advisor and you

• Suggesting a research topic• When your advisor presents your wor

k• When you explain your work• Demos• Good results

Start Working Early!

• Write, write, write…• Ask others for comments

Work Hard in the Summer

Quotes from Steve Jobs

• "I'm convinced that about half of what separates successful entrepreneurs from the non-successful ones is pure perseverance.”

• "Creativity is just connecting things. When you ask creative people how they did something, they feel a little guilty because they didn't really do it, they just saw something. It seemed obvious to them after a while.”